aimarket-oracle-gateway
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AIMARKET_HUB_URL | Yes | AIMarket Hub base URL — recommended: metered + paid, the routing fee funds the ecosystem | |
| AIMARKET_API_TOKEN | No | optional bearer token (dev/prod auth) | |
| AIMARKET_ORACLE_URL | No | direct oracle-family URL (used if no hub) — demo/free path | |
| AIMARKET_MAX_SPEND_USD | No | hard cumulative budget this process (default 5.0) — refused once exceeded | 5.0 |
| AIMARKET_PAYMENT_CHANNEL | No | optional pre-opened payment channel id (sent as X-Payment-Channel) | |
| AIMARKET_PRICE_TOLERANCE | No | reject if the hub charges > advertised × (1 + this) (default 0.10) — overcharge guard | 0.10 |
| AIMARKET_MAX_PER_CALL_USD | No | hard cap per call (default 0.10) — a call advertised above this is refused | 0.10 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_randomA | Draw unbiasable, Ed25519-signed verifiable randomness (Platon). |
| get_randomness_beaconA | Fetch the round's public randomness beacon (Platon) — one shared value all callers in the round observe, useful as a common coin / shared seed. |
| ask_oracleA | Ask the Platon oracle for a grounded, entropy-derived read-only answer. |
| verify_randomA | Verify a Platon randomness draw without re-running it (Platon verify). |
| compute_vdfA | Evaluate a Verifiable Delay Function (Chronos) — proof that real sequential work elapsed. |
| verify_vdfA | Verify a Chronos VDF proof in a single exponentiation. |
| get_reputation_scoresA | Compute PageRank/EigenTrust trust scores over a directed trust graph you supply (LUMEN). |
| get_agent_trustA | Trust score, rank, and percentile of ONE node in a trust graph you supply (LUMEN). |
| verify_reputationA | Verify LUMEN reputation scores by re-deriving PageRank over the supplied graph (LUMEN verify). |
| list_oracle_capabilitiesA | List every oracle tool with its AIMarket capabilityId and per-call price (USD). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Each tool has a distinct, clearly defined purpose: ask_oracle for queries, compute_vdf for VDF, get_agent_trust and get_reputation_scores for trust, get_random and get_randomness_beacon for randomness (one per-call, one shared beacon), list_oracle_capabilities for discovery, and three verify tools. No overlapping functionality causes ambiguity.
All tool names follow a consistent verb_noun pattern using snake_case (e.g., compute_vdf, get_random, verify_vdf). The verbs are descriptive (ask, compute, get, list, verify) and the nouns clearly indicate the resource or action. No mixing of conventions.
10 tools is well-scoped for an oracle gateway. It covers core operations (randomness, VDF, trust) plus verification and discovery without being overwhelming. Each tool earns its place; there are no redundant or trivial tools.
The tool surface is complete for the domain: it provides both per-call and beacon randomness, VDF computation, trust/reputation scoring, and separate verification for each. The inclusion of list_oracle_capabilities aids discovery. No obvious gaps like missing lifecycle operations.